rayonlabs/b35b8929-3bde-4879-89aa-c4a8dc1a74ab-9d0fa5bae69d50df_dataset_json_X-Amz-Algorithm_AWS4-HMAC-SHA

See axolotl config

axolotl version: 0.10.0.dev0

adapter: lora
base_model: samoline/b35b8929-3bde-4879-89aa-c4a8dc1a74ab
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b578b60be39aff41_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: instruct
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: deepspeed_configs/zero2.json
early_stopping_patience: 3
eval_max_new_tokens: 1024
eval_steps: 50
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
greater_is_better: false
group_by_length: false
hub_model_id: alllwang/e0020016-4788-49a3-8989-5144a1205a2d
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0008
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: -1
metric_for_best_model: eval_loss
micro_batch_size: 8
mlflow_experiment_name: /data/datasets/b578b60be39aff41_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 22dc36e2-63f4-41a1-8eb8-c0a28b2cc74b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 22dc36e2-63f4-41a1-8eb8-c0a28b2cc74b
warmup_steps: 20
weight_decay: 0.001
xformers_attention: null

e0020016-4788-49a3-8989-5144a1205a2d

This model is a fine-tuned version of samoline/b35b8929-3bde-4879-89aa-c4a8dc1a74ab on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7013

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0008
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0023	1	0.7013
0.6939	0.1159	50	0.7014
0.6923	0.2317	100	0.7013
0.714	0.3476	150	0.7013

Framework versions

• PEFT 0.15.2
• Transformers 4.52.3
• Pytorch 2.5.1+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1